[Re] Benchmarking LLM Capabilities in Negotiation through Scoreable Games
This work addresses the need for robust evaluation in multi-agent negotiation for AI researchers, but it is incremental as it builds on an existing benchmark.
The paper investigates the reproducibility and generalizability of a benchmark for evaluating LLMs in negotiation tasks, finding that while the benchmark is complex, model comparisons are ambiguous and the experimental setup has limitations.
Large Language Models (LLMs) demonstrate significant potential in multi-agent negotiation tasks, yet evaluation in this domain remains challenging due to a lack of robust and generalizable benchmarks. Abdelnabi et al. (2024) introduce a negotiation benchmark based on Scoreable Games, with the aim of developing a highly complex and realistic evaluation framework for LLMs. Our work investigates the reproducibility of claims in their benchmark, and provides a deeper understanding of its usability and generalizability. We replicate the original experiments on additional models, and introduce additional metrics to verify negotiation quality and evenness of evaluation. Our findings reveal that while the benchmark is indeed complex, model comparison is ambiguous, raising questions about its objectivity. Furthermore, we identify limitations in the experimental setup, particularly in information leakage detection and thoroughness of the ablation study. By examining and analyzing the behavior of a wider range of models on an extended version of the benchmark, we reveal insights that provide additional context to potential users. Our results highlight the importance of context in model-comparative evaluations.